Open Access
2014 Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint Sparsity
Hyuncheol Kim, Joonki Paik
Abstr. Appl. Anal. 2014: 1-12 (2014). DOI: 10.1155/2014/147353


We address object tracking problem as a multitask feature learning process based on low-rank representation of features with joint sparsity. We first select features with low-rank representation within a number of initial frames to obtain subspace basis. Next, the features represented by the low-rank and sparse property are learned using a modified joint sparsity-based multitask feature learning framework. Both the features and sparse errors are then optimally updated using a novel incremental alternating direction method. The low-rank minimization problem for learning multitask features can be achieved by a few sequences of efficient closed form update process. Since the proposed method attempts to perform the feature learning problem in both multitask and low-rank manner, it can not only reduce the dimension but also improve the tracking performance without drift. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art tracking methods for tracking objects in challenging image sequences.


Download Citation

Hyuncheol Kim. Joonki Paik. "Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint Sparsity." Abstr. Appl. Anal. 2014 1 - 12, 2014.


Published: 2014
First available in Project Euclid: 27 February 2015

zbMATH: 07021810
MathSciNet: MR3285154
Digital Object Identifier: 10.1155/2014/147353

Rights: Copyright © 2014 Hindawi

Vol.2014 • 2014
Back to Top